检索结果-内蒙古大学图书馆

Deep transfer learning technique to detect white blood cell classification in regular clinical practice using histopathological images

引用

Multimedia Tools and Applications 2025年第9期84卷 5699-5723页

作者： Davamani, K. Anita Jawahar, Malathy Anbarasi, L. Jani Ravi, Vinayakumar Al Mazroa, Alanoud Robin, C. R. Rene Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India Leather Process Technology Division CSIR-Central Leather Research Institute Chennai India School of Computing Science and Engineering Vellore Institute of Technology Vellore India Computer Science and Engineering Sri Sairam Engineering College Sirukalathur India Center for Artificial Intelligence Prince Mohammad Bin Fahd University Khobar Saudi Arabia Department of Information Systems College of Computer and Information Sciences Princess Nourah bint Abdulrahman University Riyadh11671 Saudi Arabia

Leukemia, a malignant disease characterized by the rapid proliferation of specific types of white blood cells (WBC), has prompted increased interest in leveraging automatic WBC classification system. This study presents the design of a robust WBC classification system, integrating deep learning with microscopic image analysis. The proposed classification model is designed to categorize blood cells into four distinct groups: eosinophil, lymphocyte, monocyte, and neutrophil. The study employs a Kaggle image dataset for comprehensive learning. The dataset comprises 12,500 microscopic images used to categorize the four blood cell groups. To enhance performance and reduce the likelihood of overfitting, transfer learning techniques are employed. Six deep transfer learning models namely VGG16, ResNet50, AlexNet, MobileNet, GoogLeNet, and EfficientNetBO are used for feature extraction and classification. The results of the experiments show that VGG16 and MobileNet demonstrated enhancements compared to other pre-trained models when evaluated on both augmented and original datasets. A diverse set of evaluation criteria was employed to thoroughly assess the effectiveness of medical image classification. Notably, the VGG16 and MobileNet models accurately predicted Lymphocytes and Monocytes with a 100% accuracy rate, and Eosinophil and Neutrophil with rates of 99.35% and 99.81%, respectively. This research work empower medical practitioners, particularly in the field of pathology and hematology by providing advanced tools for accurate blood cell classification. The proposed VGG16 and MobileNet models hold promise for simplifying WBC classification, improving decision-making processes, and ultimately advancing patient care in the medical domain. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

AIO-HB: A Handwritten Text Image Dataset of Hindi and Bengali indian Scripts for Handwritten Text Recognition 27th

AIO-HB: A Handwritten Text Image Dataset of Hindi and Beng...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Samanta, Piyush Kanti Biswas, Samit Department of Computer Science and Technology Indian Institute of Engineering Science and Technology Shibpur West Bengal Howrah711103 India

ISBN: (纸本)9783031784941

Document Recognition and Analysis is a long-standing area of study that has been actively investigated for many decades. Handwritten text recognition (HTR) in indian scripts is still in its early stages since the lack of publicly available datasets hampers the development of offline text recognition algorithms. Comparisons become tiresome due to the intricate structure of scripts, variances in depiction, and the presence of cursive writing. Hindi is the fourth most prevalent spoken language in the world, spoken by 615 million people, whereas Bengali is the sixth most popular, spoken by 265 million people [Source]. Both are read in a left-to-right direction. The accessible datasets of both languages are limited in size, have a limited number of writer’s samples, and use limited annotations, which poses challenges in developing resilient solutions utilising contemporary machine learning methods. Here, we have prepared Hindi and Bengali text scripts, each covering all the letters of Hindi and Bengali literature, named AIO-HB(All in one Hindi-Bengali Dataset). The dataset, which can be accessed at https://***/view/aio-hb-dataset, has also been made public for the benefit of the researchers. These handwritten scripts have been written by 202 different writers multiple times. These scripts are considered from individuals of different professions, including diverse ages and genders. The AIO-HB dataset is benchmarked using conventional deep-learning models for Handwritten Text Recognition (HTR). It can be used for various document image analysis applications, such as recognising script sentences, segmenting text lines, segmenting words, detecting words, and identifying writers. This article explores the reasons for improvements in HTR performance across scripts and the utility of annotation for indian HTRs. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

EMG Feature Selection Approach to Improve Classification Accuracy - A Review 3

EMG Feature Selection Approach to Improve Classification Acc...

引用

3rd International Conference on Secure Cyber Computing and Communications, ICSCCC 2023

作者： Agarwal, Shweta Chadha, Raman Bhati, Bhoopesh Singh Chandigarh University Computer Science & Engineering Punjab Mohali India Indian Institute of Information Technology Computer Science & Engineering Haryana Sonepat India

ISBN: (纸本)9798350300710

Nowadays, many computing systems are a part of daily life;therefore, it is more comfortable to communicate with them naturally. The field of human-computer interaction (HCI) was created in order to break down the obstacles to human-computer communication. One of the types of HCI that is, Hand Gesture Recognition (HGR), which predicts the type of a certain hand action. The electrical activity of skeletal muscles is one potential input for these types of models. The purpose of movement produced by the human brain is communicated through electromyography (EMG) signals. In order to identify EMG data that is precise for any class, the most pertinent collection of EMG attribute values must be used to train a system. With the aid of a combination of machine learning and EMG data, this paper aims to present the most recent real-time feature selection techniques and classification algorithms in a comprehensive review of the literature. Finally, several gaps have been found that may point the way for fresh lines of inquiry in the field of EMG-based gesture detection, and a proposed approach for improving the overall classification accuracy of the EMG signal is presented. © 2023 IEEE.

关键词： Human computer interaction

来源：评论

学校读者我要写书评

暂无评论

Secure key exchange protocol and storage of logic locking key 28

Secure key exchange protocol and storage of logic locking ke...

引用

28th International Symposium on VLSI Design and Test, VDAT 2024

作者： Sarojam Chellam, Manjith Baby Natarajan, Ramasubramanian Naganathan, Nagi Indian Institute of Information Technology Kottayam Department of Computer Science and Engineering-Cybersecurity Kottayam India National Institute of Technology Tiruchirappalli Department of Computer Science and Engineering Tiruchirappalli India Northrop Grumman Corporation MD United States

ISBN: (纸本)9798350380101

Logic locking has been proposed as a hardware security solution for both integrated circuits and FPGA-based design. The paper presents a secure key exchange protocol and secure LUT memory storage for the key used for unlocking the circuit. The work focuses on protecting the logic locking key for FPGA-based designs. Key exchange protocol will be accessed each time an Intellectual Property has been loaded to an FPGA. It can happen by full reconfiguration or partial reconfiguration of the bitstream. The key storage will be protected by preventing/identifying illegal access to the memory. This has been done through a firewall and access control/monitoring system. The proposed method provides security for the hardware IPs on FPGA which are locked by the logic locking method. © 2024 IEEE.

关键词： Keys (for locks)

来源：评论

学校读者我要写书评

暂无评论

Dehazing using Generative Adversarial Network - A Review

引用

SN computer science 2025年第1期6卷 1-17页

作者： Khatun, Amina Mostafiz, Rafid Shorif, Sumaita Binte Uddin, Mohammad Shorif Hadi, Md. Abdul Department of Computer Science and Engineering Jahangirnagar University Dhaka Bangladesh Institute of Information Technology Noakhali Science and Technology University Noakhali Bangladesh Department of Computer Science: Information Technology University of Nebraska Omaha Omaha United States

Dehazing is a difficult process in computer vision that seeks to improve the clarity and excellence of pictures taken under cloudy, foggy, and rainy circumstances. The Generative Adversarial Network (GAN) has been a viable method for removing haze from photos in recent years. This is because GAN can understand intricate data patterns and provide high-quality outcomes. This paper provides a thorough examination of the most advanced strategies in dehazing utilizing GAN. The study examines the various elements utilized in GAN-based dehazing, including generator and discriminator architectures, loss functions, and training strategies. It also explores the evaluation metrics employed to assess the effectiveness of GAN-based dehazing methods. It also examines the datasets often used to train and evaluate these models. This research concludes by examining prospective avenues for future study in the domain of dehazing, employing GAN to tackle the obstacles of real-time dehazing, managing intricate scenarios with various atmospheric conditions, and enhancing the resilience of GAN-based dehazing models. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： Atmospheric haze Dehazing Generative Adversarial Network (GAN) Performance evaluation metrics

来源：评论

学校读者我要写书评

暂无评论

Enhanced Cybercrime Detection on Twitter Using Aho-Corasick Algorithm and Machine Learning Techniques

引用

Informatica (Slovenia) 2024年第18期48卷 97-108页

作者： Rawat, Romil Raj, A. Samson Arun Chakrawarti, Rajesh Kumar Sankaran, Krishnan Sakthidasan Sarangi, Sanjaya Kumar Rawat, Hitesh Rawat, Anjali Department of Computer Science Engineering Shri Vaishnav Institute of Information Technology Shri Vaishnav Vidyapeeth Vishwavidyalaya Indore India Division of Computer Science and Engineering School of Computer Science and Technology Karunya Institute of Technology and Sciences Tamil Nadu Coimbatore India MP Indore India Department od Electronics and Communication Engeneering Hindustan Institute of Technology and Science Chennai India Department of Computer Science and Engineering Utkal University Bhubaneswar India Department of Business Management and Economics University of Extremadura Spain Department of Computer and Communication Technology University of Extremadura Spain

The proposed work objective is to adapt Online social networking (OSN) is a type of interactive computer-mediated technology that allows people to share information through virtual networks. The microblogging feature of Twitter makes cyberspace prominent (usually accessed via the dark web). The work used the datasets and considered the Scrape Twitter Data (Tweets) in Python using the SN-Scrape module and Twitter 4j API in JAVA to extract social data based on hashtags, which is used to select and access tweets for dataset design from a profile on the Twitter platform based on locations, keywords, and hashtags. The experiments contain two datasets. The first dataset has over 1700 tweets with a focus on location as a keypoint (hacking-for-fun data, cyber-violence data, and vulnerability injector data), whereas the second dataset only comprises 370 tweets with a focus on reposting of tweet status as a keypoint. The method used is focused on a new system model for analysing Twitter data and detecting terrorist attacks. The weights of susceptible keywords are found using a ternary search by the Aho-Corasick algorithm (ACA) for conducting signature and pattern matching. The result represents the ACA used to perform signature matching for assigning weights to extracted words of tweet. ML is used to evaluate Twitter data for classifying patterns and determining the behaviour to identify if a person is a terrorist. SVM (Support Vector Machine) proved to be a more accurate classifier for predicting terrorist attacks compared to other classifiers (KNN- K-Nearest Neighbour and NB-Naïve Bayes). The 1st dataset shows the KNN-Acc. -98.38% and SVM Accuracy as 98.85%, whereas the 2nd dataset shows the KNN-Acc. -91.68% and SVM Accuracy as 93.97%. The proposed work concludes that the generated weights are classified (cyber-violence, vulnerability injector, and hacking-for-fun) for further feature classification. Machine learning (ML) [KNN and SVM] is used to predict the occurrence and

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Hybrid Approach for Cost Efficient Application Placement in Fog-Cloud Computing Environments

引用

computers, Materials & Continua 2024年第6期79卷 4127-4148页

作者： Abdulelah Alwabel Chinmaya Kumar Swain Department of Computer Sciences College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj11942Saudi Arabia Department of Computer Science and Engineering Institute of Management and Information TechnologyCuttackBPUTOdishaIndia

Fog computing has recently developed as a new paradigm with the aim of addressing time-sensitive applications better than with cloud computing by placing and processing tasks in close proximity to the data ***,the majority of the fog nodes in this environment are geographically scattered with resources that are limited in terms of capabilities compared to cloud nodes,thus making the application placement problem more complex than that in cloud *** approach for cost-efficient application placement in fog-cloud computing environments that combines the benefits of both fog and cloud computing to optimize the placement of applications and services while minimizing *** approach is particularly relevant in scenarios where latency,resource constraints,and cost considerations are crucial factors for the deployment of *** this study,we propose a hybrid approach that combines a genetic algorithm(GA)with the Flamingo Search Algorithm(FSA)to place application modules while minimizing *** consider four cost-types for application deployment:Computation,communication,energy consumption,and *** proposed hybrid approach is called GA-FSA and is designed to place the application modules considering the deadline of the application and deploy them appropriately to fog or cloud nodes to curtail the overall cost of the *** extensive simulation is conducted to assess the performance of the proposed approach compared to other state-of-the-art *** results demonstrate that GA-FSA approach is superior to the other approaches with respect to task guarantee ratio(TGR)and total cost.

关键词： Placement mechanism application module placement fog computing cloud computing genetic algorithm flamingo search algorithm

来源：评论

学校读者我要写书评

暂无评论

Towards Autonomous Shooting Rover via Situation Aware Visual-Perception and Dynamic Action Execution

Towards Autonomous Shooting Rover via Situation Aware Visual...

引用

2024 IEEE/SICE International Symposium on System Integration, SII 2024

作者： Chikoti, Shreenaga Shubham Seelam, Yukkta Jain, Aditya Mehta, Nishi Watsa, Sidhartha Ranjan, Ayush Behera, L. Indian Institute of Technology Kanpur Department of Mathematics and Scientific Computing India Indian Institute of Technology Kanpur Department of Material Science and Engineering India Indian Institute of Technology Kanpur Department of Electrical Engineering India Indian Institute of Technology Kanpur Department of Computer Science and Engineering India Indian Institute of Technology Kanpur Department of Mechanical Engineering India

ISBN: (纸本)9798350312072

In this system paper, we present our approach to the DJI Robomaster AI Challenge, 2022 where our team ERA-IITK was ranked 3rd worldwide among 83 teams. We primarily focus on system hardware design and algorithmic components to achieve full autonomy. We first detail the hardware infrastructure, including intricate details on sensors and communication setup. Then we comprehensively describe our algorithmic pipeline and a state machine based on them to realize an autonomous system. Our major novelty is the high-speed and accurate visual perception module for target detection, and high-speed self-localization to maximize the likelihood of a target being shot. Our research endeavor in this paper can serve as a foundation for more complex systems and holds immense potential for various real-world applications. © 2024 IEEE.

关键词： Vision

来源：评论

学校读者我要写书评

暂无评论

M3Hop-CoT: Misogynous Meme Identification with Multimodal Multi-hop Chain-of-Thought

M3Hop-CoT: Misogynous Meme Identification with Multimodal Mu...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Kumari, Gitanjali Jain, Kirtan Ekbal, Asif Department of Computer Science and Engineering India Indian Institute of Technology Patna India School of AI and Data Science Indian Institute of Technology Jodhpur India

ISBN: (纸本)9798891761643

In recent years, there has been a significant rise in the phenomenon of hate against women on social media platforms, particularly through the use of misogynous memes. These memes often target women with subtle and obscure cues, making their detection a challenging task for automated systems. Recently, Large Language Models (LLMs) have shown promising results in reasoning using Chain-of-Thought (CoT) prompting to generate the intermediate reasoning chains as the rationale to facilitate multimodal tasks, but often neglect cultural diversity and key aspects like emotion and contextual knowledge hidden in the visual modalities. To address this gap, we introduce a Multimodal Multi-hop CoT (M3Hop-CoT) framework for Misogynous meme identification, combining a CLIP-based classifier and a multimodal CoT module with entity-object-relationship integration. M3Hop-CoT employs a three-step multimodal prompting principle to induce emotions, target awareness, and contextual knowledge for meme analysis. Our empirical evaluation, including both qualitative and quantitative analysis, validates the efficacy of the M3HopCoT framework on the SemEval-2022 Task 5 (MAMI task) dataset, highlighting its strong performance in the macro-F1 score. Furthermore, we evaluate the model's generalizability by evaluating it on various benchmark meme datasets, offering a thorough insight into the effectiveness of our approach across different datasets. © 2024 Association for Computational Linguistics.

关键词： Chains

来源：评论

学校读者我要写书评

暂无评论

ICRM: An intelligent citation recommendation mechanism based on BERT and weighted BoW models

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 10135-10150页

作者： Chang, Chih-Yung Yang, Yu-Ting Zhang, Qiaoyun Lin, Yi-Ti Roy, Diptendu Sinha Department of Computer Science and Information Engineering Tamkang University New Taipei Taiwan Department of English Tamkang University New Taipei Taiwan Department of Computer Science and Engineering National Institute of Technology Shillong India

With the field of technology has witnessed rapid advancements, attracting an ever-growing community of researchers dedicated to developing theories and techniques. This paper proposes an innovative ICRM (Intelligent Citation Recommendation Mechanism), designed to automate the process of suggesting the appropriate number of citations for individual brackets within a document. The proposed ICRM comprises three phases: Coarse-grained Weighted Bag of Word (WCBW), Fine-grained SciBERT (FSB) and Citation Adjustment phases. Firstly, the WCBW phase employs TF-IDF to extract keywords from both target and candidate documents, forming vectors that capture word significance along with metadata like authorship, keywords, and titles. It aims to identify relevant papers from a database, serving as initial candidates for each bracket. Secondly, the FSB phase employs the SciBERT model to assess the similarity between candidate documents and the local context around brackets, enhancing the precision of recommendations. It refines this selection by analyzing candidate-document relationships within the proximity of the brackets. Lastly, the Citation Adjustment phase tackles overlapping citations and ensures that recommended citation numbers align with user-defined criteria, resolving issues of imbalance. The simulation results demonstrate that the proposed ICRM outperforms existing models significantly in terms of precision, recall and F1-score. © 2024 - IOS Press. All rights reserved.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：